Constat — 483 Risk Radar
Use this server to query FDA and NHTSA regulatory-risk intelligence via MCP: device risk, compliance histories, premarket evidence, postmarket signals, reimbursement pathways, and vehicle safety.
device_risk_lookup: recalls, MAUDE adverse-event trend, warning-letter matches, and a composite risk score for an FDA product code.firm_compliance_history: source-bounded timeline of recalls, warning letters, 483s, and clearances for a device firm.watchlist_diff: FDA public-record changes for monitored product codes since a given date.device_evidence_lookup/evidence_search: retrieve or search parsed 510(k)/De Novo premarket evidence by product code, panel, applicant, clinical data, sensitivity metrics, or PCCP.predicate_chain: trace predicate ancestry and each predicate's age at clearance.evidence_cohort_stats: reporting-rate statistics across the parsed AI/ML corpus, with denominators.device_postmarket_lookup/postmarket_search: post-clearance recalls, MAUDE trends, warning-letter/483 matches, and drift signals for devices or cohorts.cohort_postmarket_stats: postmarket presence rates across the AI/ML device cohort.reimbursement_lookup/reimbursement_search/reimbursement_stats: trace payment pathways by K/DEN or CPT, find mechanisms, amounts, and distribution stats.vehicle_risk_lookup: NHTSA recall campaigns and complaint statistics by make/model/year.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
Constat — 483 Risk Radar (MCP server)
The MCP server behind Constat — FDA & NHTSA regulatory-risk intelligence for AI agents, over the Model Context Protocol. Live public regulatory data — recalls, adverse events, warning letters, 510(k) premarket evidence, postmarket drift signals, reimbursement pathways, and vehicle safety. Decision support, not regulatory advice.
Endpoint:
https://constat.dev/api/mcp(legacyhttps://radar.healthai.com/api/mcpstill serves)Transport: Streamable HTTP (JSON-RPC 2.0)
Auth: none for anonymous access (10 work units/min and 50/day per anonymous source); an optional
X-API-Keyheader enables the separately assigned metered allowance. Tool calls have documented work-unit costs.Registry:
com.healthai/radar(official MCP registry)
The evidence corpus and tool logic run hosted at the endpoint above. This repo
also ships server.mjs, a zero-dependency stdio bridge to that endpoint, so
stdio-only MCP clients can use the server like any local one:
node server.mjs # stdio MCP server, bridges to constat.dev/api/mcp// e.g. in an MCP client config
{ "mcpServers": { "constat": { "command": "node", "args": ["/path/to/server.mjs"] } } }docker build -t constat-mcp . && docker run -i constat-mcp # same, containerizedTools
Tool | What it does |
| FDA compliance risk for a device category by 3-letter product code — recalls, MAUDE trend, warning-letter matches, composite score |
| Source-bounded FDA public-record timeline for a device firm — recalls, warning letters, 483s, clearances |
| Machine-detected FDA public-record changes for monitored product codes since a given date |
| Parsed 510(k) premarket evidence for an AI/ML device, each field with a verbatim source quote + page |
| Find AI/ML clearances by product code, panel, applicant, clinical data, sensitivity metric, or PCCP |
| Trace a device's predicate ancestry with each predicate's age at clearance |
| Reporting-rate stats across the parsed AI/ML corpus — presence figures with denominators |
| Post-clearance intelligence for one device — recalls, MAUDE trend, letter/483 matches, drift signals |
| Find devices by postmarket criteria — drift signals, recalls in 24mo, rising MAUDE trend |
| Postmarket presence rates across the AI/ML cohort, each with its denominator |
| Clearance-to-payment pathway by K/DEN or CPT code — NTAP, Cat I/III, CMS rates, HCPCS, LCDs |
| Find payment pathways by mechanism, CPT category, NTAP status, applicant |
| Mechanism distribution across the reimbursement corpus with dollar ranges |
| NHTSA safety history by make/model/year — recall campaigns and complaint stats |
Related MCP server: fedramp-docs-mcp
Quick start
curl -s https://constat.dev/api/mcp \
-H 'content-type: application/json' \
-H 'accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call",
"params":{"name":"device_risk_lookup","arguments":{"product_code":"FRN"}}}'List tools with {"method":"tools/list"}. Note the Accept header must include
text/event-stream (streamable-HTTP requirement).
Each of the 14 tools declares an output schema. Tool calls return structured
content with an explicit ok, not_found, invalid_request, or unavailable
status while preserving a text result for older clients.
The tools are observational and non-destructive, but advertise
readOnlyHint: false because calls write bounded quota and operational-
telemetry state. They do not publish or modify FDA, CMS, NHTSA, or other
third-party records.
See the integration guide, architecture and trust boundaries, privacy notice, and support page.
Related servers
Clarity MCP — condition-aware ingredient, product & supplement safety (verdict + evidence tier + citation).
MCP Queen — the graded MCP registry that independently probes and grades this server.
About
Built by Health AI, the team behind Constat. Informational only; verify against primary FDA/NHTSA sources.
License
MIT — see LICENSE.
Available Tools
14 toolscohort_postmarket_statsBInspect
Postmarket presence rates across the snapshotted AI/ML device cohort (optionally by panel): share with any recall in 24 months, with a rising MAUDE trend, with any drift signal, with a warning-letter match — every rate with its denominator inline, never pooled across devices.
Inputs: panel.
device_evidence_lookupAInspect
Look up the structured premarket evidence FDA accepted for a specific AI/ML-enabled device by 510(k) number (e.g. K252148). Returns parsed summary fields — validation study design, sample sizes, endpoints, reported performance, predicate chain, PCCP — each with a verbatim source quote and page. Null means the summary did not state it.
Inputs: k_number (required).
device_postmarket_lookupAInspect
Post-clearance intelligence for one AI/ML device by 510(k) number: its product code's recalls, MAUDE adverse-event level and trend, warning-letter and 483 matches for the applicant, plus per-device drift signals (adverse-event inflection, re-clearances of the same device line, software-recall patterns, predicate-cohort recall activity). Descriptive observables with sources — never a safety judgment.
Inputs: k_number (required).
device_risk_lookupAInspect
Review a medical-device category's public FDA signals by three-letter product code (e.g. FRN = infusion pump). Returns recalls, MAUDE adverse-event trend, warning-letter matches, a normalized category signal, its driver contributions, and interpretation limits. It does not predict enforcement against a firm.
Inputs: product_code (required).
evidence_cohort_statsAInspect
Reporting-rate stats across the parsed AI/ML corpus (optionally by panel). Each rate is a presence figure with its denominator — 'reported in X of Y audited devices' — never a pooled performance value. Excludes not-yet-parsed devices from every denominator and discloses the parse queue separately. Predicate age (median years between a clearance and its cited predicates) is included when decision-date coverage clears a 60% floor, and withheld otherwise.
Inputs: panel.
evidence_searchAInspect
Find AI/ML device clearances by filter — product code, panel, applicant, and whether the submission reported clinical data, any sensitivity metric, or a PCCP. Answers 'what evidence did FDA accept for devices like mine'. Returns matching records with their parsed evidence. Presence flags are descriptive: 'reports a sensitivity metric' is not 'reports a comparable sensitivity' — analysis units differ across devices.
Inputs: limit, panel, has_pccp, applicant, +3 more.
firm_compliance_historyAInspect
Build a recent, source-bounded FDA public-record timeline for a device firm: matched recalls, warning letters, and Form 483 citations where exact FEI numbers are available. Product codes are discovered from Constat's AI/ML-device corpus or may be supplied explicitly. Returns attribution and coverage limits with the records; it is not a finding of noncompliance or a prediction of FDA action.
Inputs: firm_name (required), limit, since, fei_numbers, +1 more.
postmarket_searchAInspect
Find AI/ML devices by postmarket criteria — product code, panel, applicant, whether any drift signal exists, minimum recalls in 24 months, or a rising MAUDE trend. Returns per-device postmarket summaries with drift-signal counts.
Inputs: limit, panel, applicant, product_code, +4 more.
predicate_chainAInspect
Trace the predicate ancestry of a 510(k) device, with each cited predicate's age (how many years old the predicate was when the child cleared). Reveals how AI/ML devices chain to older predicates.
Inputs: k_number (required), depth.
reimbursement_lookupAInspect
Trace the clearance-to-payment pathway for an AI/ML device by FDA clearance number (K/DEN, e.g. DEN170073) OR bare CPT code (e.g. 75580). Returns every payment mechanism (NTAP add-on, Category I/III CPT + CMS rate, HCPCS, MAC LCD) with amounts, effective dates, and source links, plus any commercial/MAC payer coverage policies that reference the clearance or its codes. Answers 'who got paid, how much, through which mechanism, on what basis.' CPT codes are bare factual identifiers only — no procedure descriptors; follow the CMS source link for the official descriptor.
Inputs: cpt_code, k_number.
reimbursement_searchAInspect
Find AI/ML device payment pathways by mechanism — e.g. 'devices that got NTAP', 'devices paid under a Category I CPT code', 'pathways with a known CMS dollar rate'. Filters: mechanism, CPT category, NTAP status, applicant. Returns pathways with amounts, effective dates, and sources. Use reimbursement_stats for the mechanism distribution (never a single pooled reimbursement rate).
Inputs: limit, applicant, mechanism, ntap_status, +2 more.
reimbursement_statsAInspect
Distribution of payment mechanisms across the AI/ML reimbursement corpus — pathway and distinct-device counts per mechanism (NTAP, Cat I, Cat III/APC, …) with the min/median/max dollar amounts for each. Deliberately never a single pooled 'reimbursement rate': NTAP add-on amounts and CMS rates are different measurements and are reported separately with their own spreads.
Inputs: no named parameters.
vehicle_risk_lookupAInspect
Look up NHTSA safety history for a vehicle by make, model, and model year. Returns recall campaigns and complaint statistics (crashes, fires, injuries, top components).
Inputs: make (required), year (required), model (required).
watchlist_diffAInspect
Return machine-generated FDA public-record changes detected for monitored product codes since a caller-supplied date, plus each code's latest category snapshot and postmarket coverage. Defaults to Constat Radar's five-code watchlist and the last seven days. Analyst verdict text and internal review status are excluded; use next_since as the next polling cursor.
Inputs: limit, since, product_codes.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 14 tools
Each tool has a clearly distinct purpose: device-level premarket/postmarket lookups, firm compliance history, search across evidence/postmarket/reimbursement, statistical aggregates, predicate tracing, watchlist diff, and even a vehicle safety lookup. The detailed descriptions further minimize ambiguity.
Tool names follow a consistent pattern: domain prefix (device_, firm_, evidence_, etc.) plus operation suffix (lookup, search, stats, diff, chain). All snake_case. The sole outlier vehicle_risk_lookup still follows the same pattern, maintaining overall consistency.
14 tools is on the higher end of the ideal range (3-15) but each tool serves a specific, non-redundant purpose within the regulatory intelligence domain. The count is reasonable given the breadth of covered areas (premarket, postmarket, reimbursement, and vehicle safety).
The tool set covers the key aspects of medical device regulatory intelligence: premarket evidence, postmarket surveillance, reimbursement, firm compliance, and trend monitoring. However, the inclusion of vehicle_risk_lookup (NHTSA) is a slight domain mismatch, and there is no tool for listing or searching product codes/panels directly, though these are used as filters elsewhere.
Maintenance
Related MCP Connectors
Agent-native MCP server over 49M+ US public and government records, privacy-first, always current.
Citepath public MCP server for LLM readiness audits and public scan results.
Hosted MCP server exposing US hospital procedure cost data to AI assistants
Hosted MCP server for live public-data APIs and Skills for AI agents.
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server providing AI assistants with access to healthcare data tools, including FDA drug information, PubMed research, health topics, clinical trials, and medical terminology lookup.7132MIT
- FlicenseAqualityDmaintenanceAn unofficial MCP server that exposes public FedRAMP 20x documentation as deterministic, citable lookup tools for AI assistants, with every response citing the exact upstream source.7-
- AlicenseAqualityBmaintenanceAn MCP server that gives AI agents cited, review-gated grounding in EU regulation.555 PyPIMIT

MCP Queen Registryofficial
AlicenseAqualityCmaintenanceCrawls and grades MCP servers deterministically, providing a registry, leaderboard, and API to query server grades and submit feedback.71MIT